In [ ]:

    

import os
import ast
import glob
from scipy.misc import imread, imresize
import numpy as np
from sklearn.utils import shuffle
data_dir = '../data/dog_vs_cat'

def data_load(data_dir_path, img_height, img_width):
    """

    :param data_dir_path: data home dir
    :return: x, y    x is image content, y is category name
    """
    data_dir = data_dir_path
    subdirs = [os.path.join(data_dir, x) for x in os.listdir(data_dir)]
    x, y = [], []
    for cls in subdirs:
        imgs = glob.glob(os.path.join(cls, '*'))
        tmp_y = os.path.split(cls)[-1]
        for img_path in imgs:
            x.append(imresize(imread(img_path), (img_height, img_width)))
            y.append(tmp_y)
    return shuffle(np.array(x), y)

org_x,org_y = data_load(data_dir,224,224)
print(org_x.shape,org_y[0])
from keras.utils import to_categorical
from sklearn.preprocessing import LabelEncoder
encoder = LabelEncoder()
cate_y = to_categorical(encoder.fit_transform(org_y))


    

    




(292, 224, 224, 3) dog






    




Using TensorFlow backend.

In [ ]:

    

from keras.applications import vgg16, vgg19
model = vgg16.VGG16(input_shape=(224,224,3),weights=None,classes=2)
model.compile(loss='categorical_crossentropy',
                      optimizer='rmsprop',
                      metrics=['accuracy'])
model.fit(org_x,cate_y,validation_split=0.2,verbose=1,epochs=10)


    

    




Train on 233 samples, validate on 59 samples
Epoch 1/10
 96/233 [===========>..................] - ETA: 833s - loss: 4.5988 - acc: 0.5104 

In [ ]:

    

model = vgg19.VGG19(input_shape=(224,224,3),weights=None,classes=2)
model.compile(loss='categorical_crossentropy',
                      optimizer='rmsprop',
                      metrics=['accuracy'])
model.fit(org_x,cate_y,validation_split=0.2,verbose=1,epochs=10)